© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 62022
    Prev
    Next
    INDEX
    Explanations

    phrases that describe implementations or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oug
    -0.07
    cop
    -0.06
     ï¼ļ
    -0.06
    redo
    -0.06
     æĬķ稿
    -0.06
    lace
    -0.06
    esel
    -0.06
    arat
    -0.06
    ÏĦαν
    -0.06
    orent
    -0.06
    POSITIVE LOGITS
    gg
    0.06
    bourne
    0.06
    678
    0.06
     solicit
    0.06
    wash
    0.06
    hest
    0.06
    ivan
    0.06
    test
    0.06
     %#
    0.05
     견
    0.05
    Activations Density 0.014%

    No Known Activations